Eventos Anais de eventos
EPTT 2024
14th Spring School on Transition and Turbulence
Using convolutional neural networks to predict airfoil dynamic stall response
Submission Author:
Renato Fuzaro Miotto , SP , Brazil
Co-Authors:
Renato Fuzaro Miotto, William Wolf
Presenter: Renato Fuzaro Miotto
doi://10.26678/ABCM.EPTT2024.EPT24-0003
Abstract
Convolutional neural network models are developed to predict the aerodynamic coefficients from images of the flow field of an airfoil under dynamic stall. The networks are capable of identifying relevant flow features present in the images and associate them to the airfoil response. Results demonstrate that the models are effective in interpolating between flow parameters. Now, research is being done to verify the extrapolation capacity of the models, which will be presented in the final version of the paper. Preliminary results show that CNN-based models may offer a promising alternative for sensors in experimental campaigns and for building robust surrogate models of complex unsteady flows.
Keywords
Convolutional Neural Networks (CNN), machine learning, dynamic stall, Unsteady Aerodynamics
